{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WEKSQVVOOA5KNRK4D2JF3T4EBG","short_pith_number":"pith:WEKSQVVO","schema_version":"1.0","canonical_sha256":"b1152856ae703aa6c55c1e925dcf8409947f1984e34500e4a04f13748c898113","source":{"kind":"arxiv","id":"2403.11574","version":2},"attestation_state":"computed","paper":{"title":"Offline Multitask Representation Learning for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Doina Precup, Haque Ishfaq, Mengdi Wang, Ming Yin, Raman Arora, Songtao Feng, Thanh Nguyen-Tang","submitted_at":"2024-03-18T08:50:30Z","abstract_excerpt":"We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common representation and is asked to learn the shared representation. We theoretically investigate offline multitask low-rank RL, and propose a new algorithm called MORL for offline multitask representation learning. Furthermore, we examine downstream RL in reward-free, offline and online scenarios, where a new task is introduced to the agent that shares the same representation as the upstream offline tasks. Our theoretical re"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.11574","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-18T08:50:30Z","cross_cats_sorted":[],"title_canon_sha256":"09bbf33c5db0dc0120043f8f88ab3bed4da56d2f8ce2ed5e9ac4dfdb5fbbf210","abstract_canon_sha256":"1ab910410bbaadcec84490559481eb6998365984a58ecd477237926969ff54d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:14.097854Z","signature_b64":"T4H6x/KFs16fCRwvMXSlhktXb9JM7PTgeVY5NtpLa9oBVqtjX+uOUPCW8IQDCCvQw5gfFtolvziJTb62/ZmRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1152856ae703aa6c55c1e925dcf8409947f1984e34500e4a04f13748c898113","last_reissued_at":"2026-07-05T09:29:14.097304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:14.097304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Multitask Representation Learning for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Doina Precup, Haque Ishfaq, Mengdi Wang, Ming Yin, Raman Arora, Songtao Feng, Thanh Nguyen-Tang","submitted_at":"2024-03-18T08:50:30Z","abstract_excerpt":"We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common representation and is asked to learn the shared representation. We theoretically investigate offline multitask low-rank RL, and propose a new algorithm called MORL for offline multitask representation learning. Furthermore, we examine downstream RL in reward-free, offline and online scenarios, where a new task is introduced to the agent that shares the same representation as the upstream offline tasks. Our theoretical re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11574","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.11574/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.11574","created_at":"2026-07-05T09:29:14.097378+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11574v2","created_at":"2026-07-05T09:29:14.097378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11574","created_at":"2026-07-05T09:29:14.097378+00:00"},{"alias_kind":"pith_short_12","alias_value":"WEKSQVVOOA5K","created_at":"2026-07-05T09:29:14.097378+00:00"},{"alias_kind":"pith_short_16","alias_value":"WEKSQVVOOA5KNRK4","created_at":"2026-07-05T09:29:14.097378+00:00"},{"alias_kind":"pith_short_8","alias_value":"WEKSQVVO","created_at":"2026-07-05T09:29:14.097378+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.02834","citing_title":"Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WEKSQVVOOA5KNRK4D2JF3T4EBG","json":"https://pith.science/pith/WEKSQVVOOA5KNRK4D2JF3T4EBG.json","graph_json":"https://pith.science/api/pith-number/WEKSQVVOOA5KNRK4D2JF3T4EBG/graph.json","events_json":"https://pith.science/api/pith-number/WEKSQVVOOA5KNRK4D2JF3T4EBG/events.json","paper":"https://pith.science/paper/WEKSQVVO"},"agent_actions":{"view_html":"https://pith.science/pith/WEKSQVVOOA5KNRK4D2JF3T4EBG","download_json":"https://pith.science/pith/WEKSQVVOOA5KNRK4D2JF3T4EBG.json","view_paper":"https://pith.science/paper/WEKSQVVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11574&json=true","fetch_graph":"https://pith.science/api/pith-number/WEKSQVVOOA5KNRK4D2JF3T4EBG/graph.json","fetch_events":"https://pith.science/api/pith-number/WEKSQVVOOA5KNRK4D2JF3T4EBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WEKSQVVOOA5KNRK4D2JF3T4EBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WEKSQVVOOA5KNRK4D2JF3T4EBG/action/storage_attestation","attest_author":"https://pith.science/pith/WEKSQVVOOA5KNRK4D2JF3T4EBG/action/author_attestation","sign_citation":"https://pith.science/pith/WEKSQVVOOA5KNRK4D2JF3T4EBG/action/citation_signature","submit_replication":"https://pith.science/pith/WEKSQVVOOA5KNRK4D2JF3T4EBG/action/replication_record"}},"created_at":"2026-07-05T09:29:14.097378+00:00","updated_at":"2026-07-05T09:29:14.097378+00:00"}